Experimental Analysis and Forecasting of 17-4PH Steel in Turning Operations through TiAlN Tool Insert by Employing Artificial Neural Network and Rice Bran Oil for Sustainable Manufacturing

Abstract

Sustainable manufacturing aims to boost output while utilizing fewer resources, cutting costs, and having a smaller negative impact on the environment. Regarding the expenditure of materials, power, and resources required for creation as well as the prices of manufacturing processes, the longevity of tools used in machining operations is one of the most crucial variables in this context. The necessity to remove the produced chips, the excessive heat produced during the process, or the friction among the tool and the workpiece are all potential causes. Cutting fluid is often used to lower cutting temperatures, lower friction among the tool and the work piece, add to tool life, and enhance surface quality and machining efficiency. The current research focuses on using rice bran oil as a cooling agent to produce minimum friction and reducing the cutting forces by using a TiAlN tipped tool. Taguchi’s robust design was used to minimize the number of trials by means of L-9 orthogonal array. Speed (m/min), feed (mm/rev), depth of cut(mm), and rice bran oil (ml/min), were chosen as controllable process factors in the turning process, and surface roughness was engaged into consideration as performance evaluation features. The Taguchi analysis that revealed the appropriate process parameters markedly increased the turning performance when turned 17-4 PH, according to the results of the conformation tests. The rice bran oil used as a cutting fluid had significantly reduced the frictional forces and the tool insert could manage to cut all the nine samples with improved surface which leads to sustainable products. The Ra was mostly dependent on feed rate and rice bran oil with the respective percentage contributions of 58.06% and 49.5% respectively.